© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 23912
    Prev
    Next
    INDEX
    Explanations

    HTML table elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     we
    -2.56
     
    -1.87
    </th>
    -1.80
     you
    -1.80
     I
    -1.80
    and
    -1.80
     {
    -1.79
    </strong>
    -1.78
    」「
    -1.76
     can
    -1.73
    POSITIVE LOGITS
    “)
    2.23
    ”]
    2.19
     juſ
    2.17
    ,”
    2.16
     perpé
    2.14
    ......”
    2.11
     militer
    2.11
    鄚
    2.09
     mariana
    2.09
    ?");
    2.06
    Activations Density 0.000%

    No Known Activations